{"total":35,"rows":[{"id":"2108.03353","title":"Screen2Words: Automatic Mobile UI Summarization with Multimodal Learning","created":"2021-08-07","cited_by_count":120,"area":null},{"id":"2202.02950","title":"Jury Learning: Integrating Dissenting Voices into Machine Learning Models","created":"2022-02-07","cited_by_count":118,"area":null},{"id":"2108.01249","title":"CanvasVAE: Learning to Generate Vector Graphic Documents","created":"2021-08-03","cited_by_count":95,"area":null},{"id":"2209.08655","title":"Enabling Conversational Interaction with Mobile UI using Large Language Models","created":"2022-09-18","cited_by_count":66,"area":null},{"id":"2202.02312","title":"A Dataset for Interactive Vision-Language Navigation with Unknown Command Feasibility","created":"2022-02-04","cited_by_count":61,"area":null},{"id":"2312.03003","title":"Explore, Select, Derive, and Recall: Augmenting LLM with Human-like Memory for Mobile Task Automation","created":"2023-12-04","cited_by_count":58,"area":null},{"id":"2201.04100","title":"Learning to Denoise Raw Mobile UI Layouts for Improving Datasets at Scale","created":"2022-01-11","cited_by_count":30,"area":null},{"id":"2104.08560","title":"Mobile App Tasks with Iterative Feedback (MoTIF): Addressing Task Feasibility in Interactive Visual Environments","created":"2021-04-17","cited_by_count":28,"area":null},{"id":"2112.05692","title":"VUT: Versatile UI Transformer for Multi-Modal Multi-Task User Interface Modeling","created":"2021-12-10","cited_by_count":26,"area":null},{"id":"2210.02663","title":"Towards Better Semantic Understanding of Mobile Interfaces","created":"2022-10-06","cited_by_count":24,"area":null},{"id":"2502.16796","title":"MobileSteward: Integrating Multiple App-Oriented Agents with Self-Evolution to Automate Cross-App Instructions","created":"2025-02-24","cited_by_count":16,"area":null},{"id":"2310.15455","title":"UI Layout Generation with LLMs Guided by UI Grammar","created":"2023-10-24","cited_by_count":15,"area":null},{"id":"2410.13757","title":"MobA: Multifaceted Memory-Enhanced Adaptive Planning for Efficient Mobile Task Automation","created":"2024-10-17","cited_by_count":14,"area":null},{"id":"2105.11941","title":"Understanding Mobile GUI: from Pixel-Words to Screen-Sentences","created":"2021-05-25","cited_by_count":13,"area":null},{"id":"2310.07023","title":"Automatic Macro Mining from Interaction Traces at Scale","created":"2023-10-10","cited_by_count":12,"area":null},{"id":"2503.14021","title":"MP-GUI: Modality Perception with MLLMs for GUI Understanding","created":"2025-03-18","cited_by_count":12,"area":null},{"id":"2204.02448","title":"Predicting and Explaining Mobile UI Tappability with Vision Modeling and Saliency Analysis","created":"2022-04-05","cited_by_count":9,"area":null},{"id":"2110.07775","title":"Creating User Interface Mock-ups from High-Level Text Descriptions with Deep-Learning Models","created":"2021-10-14","cited_by_count":8,"area":null},{"id":"2404.13521","title":"Graph4GUI: Graph Neural Networks for Representing Graphical User Interfaces","created":"2024-04-21","cited_by_count":6,"area":null},{"id":"2503.03743","title":"CHOP: Mobile Operating Assistant with Constrained High-frequency Optimized Subtask Planning","created":"2025-03-05","cited_by_count":6,"area":null},{"id":"2308.05828","title":"DiLogics: Creating Web Automation Programs With Diverse Logics","created":"2023-08-10","cited_by_count":5,"area":null},{"id":"2406.07822","title":"Tell Me What's Next: Textual Foresight for Generic UI Representations","created":"2024-06-12","cited_by_count":5,"area":null},{"id":"2405.00145","title":"GUing: A Mobile GUI Search Engine using a Vision-Language Model","created":"2024-04-30","cited_by_count":4,"area":null},{"id":"2409.04081","title":"UI-JEPA: Towards Active Perception of User Intent through Onscreen User Activity","created":"2024-09-06","cited_by_count":4,"area":null},{"id":"2309.10328","title":"Computational Approaches for App-to-App Retrieval and Design Consistency Check","created":"2023-09-19","cited_by_count":3,"area":null},{"id":"2204.03731","title":"GreaseVision: Rewriting the Rules of the Interface","created":"2022-04-07","cited_by_count":2,"area":null},{"id":"2410.16430","title":"HaHeAE: Learning Generalisable Joint Representations of Human Hand and Head Movements in Extended Reality","created":"2024-10-21","cited_by_count":2,"area":null},{"id":"2411.03709","title":"AutoGameUI: Constructing High-Fidelity GameUI via Multimodal Correspondence Matching","created":"2024-11-06","cited_by_count":1,"area":null},{"id":"2509.12423","title":"Small Models, Big Results: Achieving Superior Intent Extraction through Decomposition","created":"2025-09-15","cited_by_count":1,"area":null},{"id":"2601.19171","title":"Bridging Gulfs in UI Generation through Semantic Guidance","created":"2026-01-27","cited_by_count":1,"area":null},{"id":"2403.10170","title":"Computer User Interface Understanding. A New Dataset and a Learning Framework","created":"2024-03-15","cited_by_count":0,"area":null},{"id":"2404.01240","title":"AURORA: Navigating UI Tarpits via Automated Neural Screen Understanding","created":"2024-04-01","cited_by_count":0,"area":null},{"id":"2502.03330","title":"ControlGUI: Guiding Generative GUI Exploration through Perceptual Visual Flow","created":"2025-02-05","cited_by_count":0,"area":null},{"id":"2511.19380","title":"UISearch: Graph-Based Embeddings for Multimodal Enterprise UI Screenshots Retrieval","created":"2025-11-24","cited_by_count":0,"area":null},{"id":"2609.30466","title":"A Benchmarking Framework for Context-aware XR Interfaces","created":"2026-09-24","cited_by_count":0,"area":null}],"next_cursor":null}